RAPHIA: A deep learning pipeline for the registration of MRI and whole-mount histopathology images of the prostate.

Image registration can map the ground truth extent of prostate cancer from histopathology images onto MRI, facilitating the development of machine learning methods for early prostate cancer detection. Here, we present RAdiology PatHology Image Alignment (RAPHIA), an end-to-end pipeline for efficient and accurate registration of MRI and histopathology images. RAPHIA automates several time-consuming manual steps in existing approaches including prostate segmentation, estimation of the rotation angle and horizontal flipping in histopathology images, and estimation of MRI-histopathology slice correspondences. By utilizing deep learning registration networks, RAPHIA substantially reduces computational time. Furthermore, RAPHIA obviates the need for a multimodal image similarity metric by transferring histopathology image representations to MRI image representations and vice versa. With the assistance of RAPHIA, novice users achieved expert-level performance, and their mean error in estimating histopathology rotation angle was reduced by 51% (12 degrees vs 8 degrees), their mean accuracy of estimating histopathology flipping was increased by 5% (95.3% vs 100%), and their mean error in estimating MRI-histopathology slice correspondences was reduced by 45% (1.12 slices vs 0.62 slices). When compared to a recent conventional registration approach and a deep learning registration approach, RAPHIA achieved better mapping of histopathology cancer labels, with an improved mean Dice coefficient of cancer regions outlined on MRI and the deformed histopathology (0.44 vs 0.48 vs 0.50), and a reduced mean per-case processing time (51 vs 11 vs 4.5 min). The improved performance by RAPHIA allows efficient processing of large datasets for the development of machine learning models for prostate cancer detection on MRI. Our code is publicly available at: https://github.com/pimed/RAPHIA.

Antipsychotic Medication and Risk of Metabolic Disorders in People With Schizophrenia: A Longitudinal Study Using the UK Clinical Practice Research Datalink.

BACKGROUND AND HYPOTHESIS: Antipsychotics are first-line drug treatments for schizophrenia. When antipsychotic monotherapy is ineffective, combining two antipsychotic drugs is common although treatment guidelines warn of possible increases in side effects. Risks of metabolic side effects with antipsychotic polypharmacy have not been fully investigated. This study examined associations between antipsychotic polypharmacy and risk of developing diabetes, hypertension, or hyperlipidemia in adults with schizophrenia, and impact of co-prescription of first- and second-generation antipsychotics. STUDY DESIGN: A population-based prospective cohort study was conducted in the United Kingdom using linked primary care, secondary care, mental health, and social deprivation datasets. Cox proportional hazards models with stabilizing weights were used to estimate risk of metabolic disorders among adults with schizophrenia, comparing patients on antipsychotic monotherapy vs polypharmacy, adjusting for demographic and clinical characteristics, and antipsychotic dose. STUDY RESULTS: Median follow-up time across the three cohorts was approximately 14 months. 6.6% developed hypertension in the cohort assembled for this outcome, with polypharmacy conferring an increased risk compared to monotherapy, (adjusted Hazard Ratio = 3.16; P = .021). Patients exposed to exclusive first-generation antipsychotic polypharmacy had greater risk of hypertension compared to those exposed to combined first- and second-generation polypharmacy (adjusted HR 0.29, P = .039). No associations between polypharmacy and risk of diabetes or hyperlipidemia were found. CONCLUSIONS: Antipsychotic polypharmacy, particularly polypharmacy solely comprised of first-generation antipsychotics, increased the risk of hypertension. Future research employing larger samples, follow-up longer than the current median of 14 months, and more complex methodologies may further elucidate the association reported in this study.

A review of artificial intelligence in prostate cancer detection on imaging.

A multitude of studies have explored the role of artificial intelligence (AI) in providing diagnostic support to radiologists, pathologists, and urologists in prostate cancer detection, risk-stratification, and management. This review provides a comprehensive overview of relevant literature regarding the use of AI models in (1) detecting prostate cancer on radiology images (magnetic resonance and ultrasound imaging), (2) detecting prostate cancer on histopathology images of prostate biopsy tissue, and (3) assisting in supporting tasks for prostate cancer detection (prostate gland segmentation, MRI-histopathology registration, MRI-ultrasound registration). We discuss both the potential of these AI models to assist in the clinical workflow of prostate cancer diagnosis, as well as the current limitations including variability in training data sets, algorithms, and evaluation criteria. We also discuss ongoing challenges and what is needed to bridge the gap between academic research on AI for prostate cancer and commercial solutions that improve routine clinical care.

Bridging the gap between prostate radiology and pathology through machine learning.

BACKGROUND: Prostate cancer remains the second deadliest cancer for American men despite clinical advancements. Currently, magnetic resonance imaging (MRI) is considered the most sensitive non-invasive imaging modality that enables visualization, detection, and localization of prostate cancer, and is increasingly used to guide targeted biopsies for prostate cancer diagnosis. However, its utility remains limited due to high rates of false positives and false negatives as well as low inter-reader agreements. PURPOSE: Machine learning methods to detect and localize cancer on prostate MRI can help standardize radiologist interpretations. However, existing machine learning methods vary not only in model architecture, but also in the ground truth labeling strategies used for model training. We compare different labeling strategies and the effects they have on the performance of different machine learning models for prostate cancer detection on MRI. METHODS: Four different deep learning models (SPCNet, U-Net, branched U-Net, and DeepLabv3+) were trained to detect prostate cancer on MRI using 75 patients with radical prostatectomy, and evaluated using 40 patients with radical prostatectomy and 275 patients with targeted biopsy. Each deep learning model was trained with four different label types: pathology-confirmed radiologist labels, pathologist labels on whole-mount histopathology images, and lesion-level and pixel-level digital pathologist labels (previously validated deep learning algorithm on histopathology images to predict pixel-level Gleason patterns) on whole-mount histopathology images. The pathologist and digital pathologist labels (collectively referred to as pathology labels) were mapped onto pre-operative MRI using an automated MRI-histopathology registration platform. RESULTS: Radiologist labels missed cancers (ROC-AUC: 0.75-0.84), had lower lesion volumes (~68% of pathology lesions), and lower Dice overlaps (0.24-0.28) when compared with pathology labels. Consequently, machine learning models trained with radiologist labels also showed inferior performance compared to models trained with pathology labels. Digital pathologist labels showed high concordance with pathologist labels of cancer (lesion ROC-AUC: 0.97-1, lesion Dice: 0.75-0.93). Machine learning models trained with digital pathologist labels had the highest lesion detection rates in the radical prostatectomy cohort (aggressive lesion ROC-AUC: 0.91-0.94), and had generalizable and comparable performance to pathologist label-trained-models in the targeted biopsy cohort (aggressive lesion ROC-AUC: 0.87-0.88), irrespective of the deep learning architecture. Moreover, machine learning models trained with pixel-level digital pathologist labels were able to selectively identify aggressive and indolent cancer components in mixed lesions on MRI, which is not possible with any human-annotated label type. CONCLUSIONS: Machine learning models for prostate MRI interpretation that are trained with digital pathologist labels showed higher or comparable performance with pathologist label-trained models in both radical prostatectomy and targeted biopsy cohort. Digital pathologist labels can reduce challenges associated with human annotations, including labor, time, inter- and intra-reader variability, and can help bridge the gap between prostate radiology and pathology by enabling the training of reliable machine learning models to detect and localize prostate cancer on MRI.

Impact of standardizing care for agitation in dementia using an integrated care pathway on an inpatient geriatric psychiatry unit.

OBJECTIVES: This study examined the effectiveness of an integrated care pathway (ICP), including a medication algorithm, to treat agitation associated with dementia. DESIGN: Analyses of data (both prospective and retrospective) collected during routine clinical care. SETTING: Geriatric Psychiatry Inpatient Unit. PARTICIPANTS: Patients with agitation associated with dementia (n = 28) who were treated as part of the implementation of the ICP and those who received treatment-as-usual (TAU) (n = 28) on the same inpatient unit before the implementation of the ICP. Two control groups of patients without dementia treated on the same unit contemporaneously to the TAU (n = 17) and ICP groups (n = 36) were included to account for any secular trends. INTERVENTION: ICP. MEASUREMENTS: Cohen Mansfield Agitation Inventory (CMAI), Neuropsychiatric Inventory Questionnaire (NPIQ), and assessment of motor symptoms were completed during the ICP implementation. Chart review was used to obtain length of inpatient stay and rates of psychotropic polypharmacy. RESULTS: Patients in the ICP group experienced a reduction in their scores on the CMAI and NPIQ and no changes in motor symptoms. Compared to the TAU group, the ICP group had a higher chance of an earlier discharge from hospital, a lower rate of psychotropic polypharmacy, and a lower chance of having a fall during hospital stay. In contrast, these outcomes did not differ between the two control groups. CONCLUSIONS: These preliminary results suggest that an ICP can be used effectively to treat agitation associated with dementia in inpatients. A larger randomized study is needed to confirm these results.

Selective identification and localization of indolent and aggressive prostate cancers via CorrSigNIA: an MRI-pathology correlation and deep learning framework.

Automated methods for detecting prostate cancer and distinguishing indolent from aggressive disease on Magnetic Resonance Imaging (MRI) could assist in early diagnosis and treatment planning. Existing automated methods of prostate cancer detection mostly rely on ground truth labels with limited accuracy, ignore disease pathology characteristics observed on resected tissue, and cannot selectively identify aggressive (Gleason Pattern≥4) and indolent (Gleason Pattern=3) cancers when they co-exist in mixed lesions. In this paper, we present a radiology-pathology fusion approach, CorrSigNIA, for the selective identification and localization of indolent and aggressive prostate cancer on MRI. CorrSigNIA uses registered MRI and whole-mount histopathology images from radical prostatectomy patients to derive accurate ground truth labels and learn correlated features between radiology and pathology images. These correlated features are then used in a convolutional neural network architecture to detect and localize normal tissue, indolent cancer, and aggressive cancer on prostate MRI. CorrSigNIA was trained and validated on a dataset of 98 men, including 74 men that underwent radical prostatectomy and 24 men with normal prostate MRI. CorrSigNIA was tested on three independent test sets including 55 men that underwent radical prostatectomy, 275 men that underwent targeted biopsies, and 15 men with normal prostate MRI. CorrSigNIA achieved an accuracy of 80% in distinguishing between men with and without cancer, a lesion-level ROC-AUC of 0.81±0.31 in detecting cancers in both radical prostatectomy and biopsy cohort patients, and lesion-levels ROC-AUCs of 0.82±0.31 and 0.86±0.26 in detecting clinically significant cancers in radical prostatectomy and biopsy cohort patients respectively. CorrSigNIA consistently outperformed other methods across different evaluation metrics and cohorts. In clinical settings, CorrSigNIA may be used in prostate cancer detection as well as in selective identification of indolent and aggressive components of prostate cancer, thereby improving prostate cancer care by helping guide targeted biopsies, reducing unnecessary biopsies, and selecting and planning treatment.

Electronic Health Records-Based Cardio-Oncology Registry for Care Gap Identification and Pragmatic Research: Procedure and Observational Study.

BACKGROUND: Professional society guidelines are emerging for cardiovascular care in cancer patients. However, it is not yet clear how effectively the cancer survivor population is screened and treated for cardiomyopathy in contemporary clinical practice. As electronic health records (EHRs) are now widely used in clinical practice, we tested the hypothesis that an EHR-based cardio-oncology registry can address these questions. OBJECTIVE: The aim of this study was to develop an EHR-based pragmatic cardio-oncology registry and, as proof of principle, to investigate care gaps in the cardiovascular care of cancer patients. METHODS: We generated a programmatically deidentified, real-time EHR-based cardio-oncology registry from all patients in our institutional Cancer Population Registry (N=8275, 2011-2017). We investigated: (1) left ventricular ejection fraction (LVEF) assessment before and after treatment with potentially cardiotoxic agents; and (2) guideline-directed medical therapy (GDMT) for left ventricular dysfunction (LVD), defined as LVEF<50%, and symptomatic heart failure with reduced LVEF (HFrEF), defined as LVEF<50% and Problem List documentation of systolic congestive heart failure or dilated cardiomyopathy. RESULTS: Rapid development of an EHR-based cardio-oncology registry was feasible. Identification of tests and outcomes was similar using the EHR-based cardio-oncology registry and manual chart abstraction (100% sensitivity and 83% specificity for LVD). LVEF was documented prior to initiation of cancer therapy in 19.8% of patients. Prevalence of postchemotherapy LVD and HFrEF was relatively low (9.4% and 2.5%, respectively). Among patients with postchemotherapy LVD or HFrEF, those referred to cardiology had a significantly higher prescription rate of a GDMT. CONCLUSIONS: EHR data can efficiently populate a real-time, pragmatic cardio-oncology registry as a byproduct of clinical care for health care delivery investigations.

Automated detection of aggressive and indolent prostate cancer on magnetic resonance imaging.

PURPOSE: While multi-parametric magnetic resonance imaging (MRI) shows great promise in assisting with prostate cancer diagnosis and localization, subtle differences in appearance between cancer and normal tissue lead to many false positive and false negative interpretations by radiologists. We sought to automatically detect aggressive cancer (Gleason pattern ≥ 4) and indolent cancer (Gleason pattern 3) on a per-pixel basis on MRI to facilitate the targeting of aggressive cancer during biopsy. METHODS: We created the Stanford Prostate Cancer Network (SPCNet), a convolutional neural network model, trained to distinguish between aggressive cancer, indolent cancer, and normal tissue on MRI. Ground truth cancer labels were obtained by registering MRI with whole-mount digital histopathology images from patients who underwent radical prostatectomy. Before registration, these histopathology images were automatically annotated to show Gleason patterns on a per-pixel basis. The model was trained on data from 78 patients who underwent radical prostatectomy and 24 patients without prostate cancer. The model was evaluated on a pixel and lesion level in 322 patients, including six patients with normal MRI and no cancer, 23 patients who underwent radical prostatectomy, and 293 patients who underwent biopsy. Moreover, we assessed the ability of our model to detect clinically significant cancer (lesions with an aggressive component) and compared it to the performance of radiologists. RESULTS: Our model detected clinically significant lesions with an area under the receiver operator characteristics curve of 0.75 for radical prostatectomy patients and 0.80 for biopsy patients. Moreover, the model detected up to 18% of lesions missed by radiologists, and overall had a sensitivity and specificity that approached that of radiologists in detecting clinically significant cancer. CONCLUSIONS: Our SPCNet model accurately detected aggressive prostate cancer. Its performance approached that of radiologists, and it helped identify lesions otherwise missed by radiologists. Our model has the potential to assist physicians in specifically targeting the aggressive component of prostate cancers during biopsy or focal treatment.

3D Registration of pre-surgical prostate MRI and histopathology images via super-resolution volume reconstruction.

The use of MRI for prostate cancer diagnosis and treatment is increasing rapidly. However, identifying the presence and extent of cancer on MRI remains challenging, leading to high variability in detection even among expert radiologists. Improvement in cancer detection on MRI is essential to reducing this variability and maximizing the clinical utility of MRI. To date, such improvement has been limited by the lack of accurately labeled MRI datasets. Data from patients who underwent radical prostatectomy enables the spatial alignment of digitized histopathology images of the resected prostate with corresponding pre-surgical MRI. This alignment facilitates the delineation of detailed cancer labels on MRI via the projection of cancer from histopathology images onto MRI. We introduce a framework that performs 3D registration of whole-mount histopathology images to pre-surgical MRI in three steps. First, we developed a novel multi-image super-resolution generative adversarial network (miSRGAN), which learns information useful for 3D registration by producing a reconstructed 3D MRI. Second, we trained the network to learn information between histopathology slices to facilitate the application of 3D registration methods. Third, we registered the reconstructed 3D histopathology volumes to the reconstructed 3D MRI, mapping the extent of cancer from histopathology images onto MRI without the need for slice-to-slice correspondence. When compared to interpolation methods, our super-resolution reconstruction resulted in the highest PSNR relative to clinical 3D MRI (32.15 dB vs 30.16 dB for BSpline interpolation). Moreover, the registration of 3D volumes reconstructed via super-resolution for both MRI and histopathology images showed the best alignment of cancer regions when compared to (1) the state-of-the-art RAPSODI approach, (2) volumes that were not reconstructed, or (3) volumes that were reconstructed using nearest neighbor, linear, or BSpline interpolations. The improved 3D alignment of histopathology images and MRI facilitates the projection of accurate cancer labels on MRI, allowing for the development of improved MRI interpretation schemes and machine learning models to automatically detect cancer on MRI.

ProsRegNet: A deep learning framework for registration of MRI and histopathology images of the prostate.

Magnetic resonance imaging (MRI) is an increasingly important tool for the diagnosis and treatment of prostate cancer. However, interpretation of MRI suffers from high inter-observer variability across radiologists, thereby contributing to missed clinically significant cancers, overdiagnosed low-risk cancers, and frequent false positives. Interpretation of MRI could be greatly improved by providing radiologists with an answer key that clearly shows cancer locations on MRI. Registration of histopathology images from patients who had radical prostatectomy to pre-operative MRI allows such mapping of ground truth cancer labels onto MRI. However, traditional MRI-histopathology registration approaches are computationally expensive and require careful choices of the cost function and registration hyperparameters. This paper presents ProsRegNet, a deep learning-based pipeline to accelerate and simplify MRI-histopathology image registration in prostate cancer. Our pipeline consists of image preprocessing, estimation of affine and deformable transformations by deep neural networks, and mapping cancer labels from histopathology images onto MRI using estimated transformations. We trained our neural network using MR and histopathology images of 99 patients from our internal cohort (Cohort 1) and evaluated its performance using 53 patients from three different cohorts (an additional 12 from Cohort 1 and 41 from two public cohorts). Results show that our deep learning pipeline has achieved more accurate registration results and is at least 20 times faster than a state-of-the-art registration algorithm. This important advance will provide radiologists with highly accurate prostate MRI answer keys, thereby facilitating improvements in the detection of prostate cancer on MRI. Our code is freely available at https://github.com/pimed//ProsRegNet.

Registration of presurgical MRI and histopathology images from radical prostatectomy via RAPSODI.

PURPOSE: Magnetic resonance imaging (MRI) has great potential to improve prostate cancer diagnosis; however, subtle differences between cancer and confounding conditions render prostate MRI interpretation challenging. The tissue collected from patients who undergo radical prostatectomy provides a unique opportunity to correlate histopathology images of the prostate with preoperative MRI to accurately map the extent of cancer from histopathology images onto MRI. We seek to develop an open-source, easy-to-use platform to align presurgical MRI and histopathology images of resected prostates in patients who underwent radical prostatectomy to create accurate cancer labels on MRI. METHODS: Here, we introduce RAdiology Pathology Spatial Open-Source multi-Dimensional Integration (RAPSODI), the first open-source framework for the registration of radiology and pathology images. RAPSODI relies on three steps. First, it creates a three-dimensional (3D) reconstruction of the histopathology specimen as a digital representation of the tissue before gross sectioning. Second, RAPSODI registers corresponding histopathology and MRI slices. Third, the optimized transforms are applied to the cancer regions outlined on the histopathology images to project those labels onto the preoperative MRI. RESULTS: We tested RAPSODI in a phantom study where we simulated various conditions, for example, tissue shrinkage during fixation. Our experiments showed that RAPSODI can reliably correct multiple artifacts. We also evaluated RAPSODI in 157 patients from three institutions that underwent radical prostatectomy and have very different pathology processing and scanning. RAPSODI was evaluated in 907 corresponding histpathology-MRI slices and achieved a Dice coefficient of 0.97 ± 0.01 for the prostate, a Hausdorff distance of 1.99 ± 0.70 mm for the prostate boundary, a urethra deviation of 3.09 ± 1.45 mm, and a landmark deviation of 2.80 ± 0.59 mm between registered histopathology images and MRI. CONCLUSION: Our robust framework successfully mapped the extent of cancer from histopathology slices onto MRI providing labels from training machine learning methods to detect cancer on MRI.

Evaluation of digital staining for ex vivo confocal laser scanning microscopy.

BACKGROUND: Ex vivo confocal laser scanning microscopy (CLSM) is a novel diagnostic tool for the fast examination of native tissue. However, CLSM produces black/white/green images, depending on the refraction indices of the tissue structures, complemented by nuclear fluorescence staining, which the vast majority of Mohs surgeons and dermatopathologists are not trained to interpret. Digital staining is applicable to ex vivo CLSM investigations to simulate the images of conventional slides stained with haematoxylin and eosin (H&E). OBJECTIVES: The aim of our study was to evaluate in detail the appearance of human skin structures using digitally stained ex vivo CLSM images and compare the results to that of conventional H&E slides of the same specimen. METHODS: After providing informed consent, 26 patients donated their Burow's triangles (healthy skin) that resulted from plastic reconstruction after the R0 excision of skin tumours. After being investigated by ex vivo CLSM, including automated digital staining (VivaScope 2500M-4G, MAVIG GmbH), the specimens were fixed in formalin, embedded in paraffin and stained with H&E. RESULTS: Almost all skin structures in the digitally stained ex vivo CLSM images morphologically resembled the structures in the histopathological images acquired from H&E slides. Due to the high refraction index of melanin, the hair shafts appeared bright pink, and the melanocytes and melanophages were poorly imaged, resulting in a strong pink appearance that vastly differed from the appearance of conventional H&E-stained histopathology. CONCLUSIONS: Digital staining of ex vivo CLSM images is an easy and highly useful tool to facilitate the interpretation of black-field images generated by confocal laser scanning microscopy for dermatopathologists and Mohs surgeons who are familiar with H&E staining. Unlike the pigmented structures, the cutaneous and subcutaneous structures had excellent visualization with only minimal differences from their appearance on H&E slides.

Depression, anxiety and quality of life in subjects with atopic eczema in a population-based cross-sectional study in Germany.

BACKGROUND: Atopic eczema (AE) may be associated with several mental health problems. In Germany, existing data from selected patient cohorts may lead to misestimation of the problem. OBJECTIVES: We aimed to cross-sectionally determine associations of AE with depression, anxiety, quality of life (QoL) and social interactions in subjects from the population-based LIFE-Adult-Study. METHODS: Subjects underwent standardized interviews (medical history) and answered standardized questionnaires [Centre of Epidemiologic studies-Depression scale (CES-D), Generalized Anxiety Disorder (GAD-7), Lubben Social Network Scale (LSNS), Short Form Health Survey (SF-8)]. We compared data from subjects with AE with those from subjects with selected other chronic/disabling diseases (cardiovascular, diabetes, cancer) and adjusted for selected sociodemographic parameters. Multivariate binary logistic regression was used for categorical variables, linear regression for continuous variables. RESULTS: Out of 9104 adults included (57% female, median age 54 years), 372 (4.1%) had a history of AE. Compared with controls, subjects with AE showed higher scores for depressive symptoms (9.3% vs. 6.3%; P < 0.001) and anxiety (8.4% vs. 5.6%, P < 0.001). Odds ratio (OR) was 1.5 [CI 1.0; 2.3] (P = 0.031) for depression, which was comparable to OR in patients with a history of cancer (OR 1.6 [1-2.3], P = 0.001. OR for anxiety in AE was 1.5 [1.0; 2.2], P < 0.049, which was slightly higher than in diabetes mellitus (OR 1.2) and stroke (OR 1.4). Other than in diabetes and/or stroke, we did not find a significant association between AE and social isolation. QoL scores were lower in AE than in controls (mean 46.9 vs. 48.0, P < 0.001 for physical and 50.6 vs. 52.5, P < 0.001 for mental components). CONCLUSIONS: Subjects with AE showed higher values for depression and anxiety as well as lower QoL scores compared to controls. With regard to depression, odds in AE and cancer were hardly different. Medical care of AE patients should therefore include mental health evaluation and treatment if indicated.

[Malignant collision tumor of the skin : Melanoma, squamous cell carcinoma and basal cell carcinoma]. / Maligner Kollisionstumor der Haut : Melanom, kutanes Plattenepithelkarzinom und Basalzellkarzinom.

We present the case of a woman in her eighties with a collision tumor composed of a malignant melanoma, a squamous cell carcinoma and a basal cell carcinoma. The simultaneous growth of histogenetically different, spatially not separate, malignant tumors of the skin is rare. The classification is difficult and sometimes confusing, especially regarding the terminology used in the literature. The correct classification of such tumors has a high significance for the clinical daily routine.

[Smooth muscle hamartoma in volar skin]. / Glattmuskelhamartom in volarer Haut.

We report the case of a 12-year-old girl with a smooth muscle hamartoma of the right index finger. Smooth muscle hamartoma (SMH) is a congenital, relatively common disorder typically with predominance of autochthonal arrector pili muscles. An SMH can also rarely originate from smooth muscles of vessels in palmoplantar skin with the absence of pilosebaceous units. Because of overlapping histological features, the possibility of Becker's nevus being identical or associated with SMH has often been suspected by some authors.